UOW-Vessel: A Benchmark Dataset of High-Resolution Optical Satellite Images for Vessel Detection and Segmentation
We introduce UOW-Vessel, a new benchmark dataset of high-resolution optical satellite images for vessel detection and segmentation. Our dataset consists of 3,500 images, collected from 14 countries across 4 continents. With a total of 35,598 instances in 10 vessel categories, UOW-Vessel is the largest satellite image dataset for vessel recognition. Furthermore, compared to the existing public datasets that only provide bounding box ground-truth, our new dataset offers more accurate polygon annotations of vessel objects. Our dataset is expected to support segmentation-based approaches, which is a less investigated area in vessel surveillance.
The vessel categories present in our dataset include: Aircraft Carrier (AC), Landing (LL), Cruiser (CG), Destroyer (DD), Frigate (FF), Patrol (PB), Corvette (CT), Submarine (SS), Other Military (OM), and Civilian (CV). The class “Other Military” contains auxiliary vessels such as training ships, survey ships, medical ships and oil replenishment ships.
Category | No. Instances | Proportion |
---|---|---|
Aircraft Carrier | 180 | 0.51% |
Landing | 1,078 | 3.03% |
Cruiser | 215 | 0.60% |
Destroyer | 746 | 2.10% |
Frigate | 963 | 2.71% |
Patrol | 1,437 | 4.04% |
Corvette | 622 | 1.75% |
Submarine | 845 | 2.37% |
Other Military | 5,105 | 14.34% |
Civilian | 24,407 | 68.56% |
Total | 35,598 | 100.00% |